Knowledge distillation (KD) aims to enhance the performance of lightweight student networks through the guidance of teacher models. However, the existing methods have deficiencies in two key aspects: First, these methods rely heavily on static representation alignment, failing to account for optimization sensitivity in different directions within the distillation subspace; second, they lack a fine-grained mechanism to align critical directional features. To address these issues, we propose Direction Sensitivity–based Knowledge Distillation method (DSKD), which can quantitatively measure the sensitivity of each direction to the loss function at different training stages and dynamically select the optimization direction accordingly. Meanwhile, we designed a directional sensitivities weighted distillation loss. By aligning the parameter matrices of the teacher and student models in the key directions, we can more effectively transfer knowledge and improve the distillation effect. We combined DSKD with multiple advanced distillation strategies and conducted an empirical evaluation in the GLUE benchmark and CIFAR-100. The results showed that this method could significantly improve the performance of existing distillation techniques.

Physiological signal-based emotion recognition requires effective fusion of multi-modal physiological signals to improve recognition accuracy. In this paper, a multi-kernel embedding fusion framework (MKEFF) is proposed for multi-modal physiological signal emotion recognition. Specifically, multi-kernel learning and kernel approximation techniques are used to compute the multi-kernel embeddings of the original feature vectors of each modality independently. The embeddings are then fed in parallel to their respective representation learning layer, where the proposed sparse relation learning method is applied to all the modalities to explore the correlation and diversity among them. Finally, a distribution alignment based fusion method is proposed to align each modality in the subspace, and a weighted summation fusion is performed to obtain the fused representations. Extensive cross-subject emotion recognition experiments are conducted on three public datasets, DEAP, DECAF, and SEED-IV, to evaluate the proposed method. The experimental results demonstrate that the proposed method achieves better classification performance and interpretability than the state-of-the-art methods.

Current research on grasping state analysis in soft manipulators is limited and lacks broad applicability. In this article, we introduce a novel method that leverages multimodal data from flexible sensors and Inertial Measurement Units (IMUs) to develop a comprehensive grasping state analysis system for multidegree-of-freedom (multi-DOF) pneumatic soft manipulators. A Deep Spiking High-Dimensional Fuzzy Network (DSHTFN) algorithm is specifically designed to analyze the “3S” grasping states of soft manipulators—shaking, stable, and slipping—with greater depth and precision. A novel membership function, the BernoulliArctangent (B-Atan) function, has been designed to accommodate the unique characteristics of spiking input signals and support backpropagation capabilities. Experimental results demonstrate that our proposed method achieves accuracies of 95.66% and 96.05% in opposing-finger and three-fingered soft manipulator operations, respectively. Through comparative analysis with other algorithms, the superior performance of the B-Atan membership function and the DSHTFN approach in analyzing the grasping states of soft manipulators has been validated.

In recent years, the rapid growth of remote sensing (RS) datasets has greatly enhanced the difficulty of RS image classification tasks. Given the remarkable success of large visual-language models (VLMs) in various domains, their potential for RS image classification tasks has attracted significant attention. In this study, we focus on Contrastive Language-Image Pre-training (CLIP), a widely recognized contrastive learning model known for its strong zero-shot transferability. However, the domain gap between the pre-training data (e.g., natural images) of CLIP and RS data can significantly hinder the application of CLIP. First, the scarcity of labeled RS data poses a significant challenge for fine-tuning CLIP. Second, the complexity and diversity of RS images substantially increase the fine-tuning time and computational resources needed to individually adapt CLIP to new tasks. Third, independently fine-tuning CLIP for each RS dataset ignores the inter-task relationships that frequently exist among remote sensing images from various sources, leading to reduced classification accuracy. To address these challenges, we propose a learnable Mixture of Adapters (MoA) module in the visual branch of CLIP, resulting in the CLIP-MoA framework. Inspired by the Mixture of Experts (MoE), the MoA module models inter-dataset relationships by integrating multiple adapters through a gating network, while preserving original information via a residual connection between the MoA input and the fine-tuned features. This module enables CLIP-MoA to effectively capture both inter-task commonalities and task-specific characteristics by fine-tuning a minimal set of MoA parameters across multiple datasets simultaneously, thereby reducing computational overhead and fine-tuning time while improving classification accuracy. Comprehensive experiments conducted on a multi-task benchmark involving 11 remote sensing image classification datasets demonstrate that CLIP-MoA achieves significant improvements in both classification accuracy and generalization capability compared to zero-shot CLIP, linear probe CLIP, CLIP-Adapter, and CoOp.

Supernumerary robotic limbs (SRLs) offer substantial potential in both the rehabilitation of hemiplegic patients and the enhancement of functional capabilities for healthy individuals. Designing a general-purpose SRL device is inherently challenging, particularly when developing a unified theoretical framework that meets the diverse functional requirements of both upper and lower limbs. In this paper, we propose a multi-objective optimization (MOO) design theory that integrates grasping workspace similarity, walking workspace similarity, braced force for sit-to-stand (STS) movements, and overall mass and inertia. A geometric vector quantification method is developed using an ellipsoid to represent the workspace, aiming to reduce computational complexity and address quantification challenges. The ellipsoid envelope transforms workspace points into ellipsoid attributes, providing a parametric description of the workspace. Furthermore, the STS static braced force assesses the effectiveness of force transmission. The overall mass and inertia restricts excessive link length. To facilitate rapid and stable convergence of the model to high-dimensional irregular Pareto fronts, we introduce a multi-subpopulation correction firefly algorithm. This algorithm incorporates a strategy involving attractive and repulsive domains to effectively handle the MOO task. The optimized solution is utilized to redesign the prototype for experimentation to meet specified requirements. Six healthy participants and two hemiplegia patients participated in real experiments. Compared to the pre-optimization results, the average grasp success rate improved by 7.2%, while the muscle activity during walking and STS tasks decreased by an average of 12.7% and 25.1%, respectively. The proposed design theory offers an efficient option for the design of multi-functional SRL mechanisms.

Lower-limb motion intent recognition is a crucial aspect of wearable robot control and human-machine collaboration. Among the various sensors used for this purpose, the electromyogram (EMG) sensor remains one of the most widely employed. However, EMG signals are highly susceptible to electrical noise, motion artefacts, and perspiration, which can compromise their quality. To address these challenges, we designed an air-pressure mechanomyography (PMMG) sensor and developed a wearable multi-modal sensor system that incorporates PMMG thigh-ring, inertial measurement unit (IMU), and force-sensitive resistor (FSR). To enhance gait phase and locomotion mode recognition performance, we proposed a gate multi-task TSK fuzzy inference system (GMT-TSK-FIS) algorithm that enables simultaneous handling of multiple recognition tasks. This approach enabled the development of a lower-limb motion intent recognition system that can simultaneously recognize gait phase and locomotion mode based on GMT-TSK-FIS. The experimental results showed that the accuracy of gait phase and locomotion mode recognition was 98.28% and 99.96%, respectively. Furthermore, the study demonstrated that multi-modal sensor fusion outperformed single-modal sensor fusion, while multi-task recognition exhibited better performance than single-task recognition.